Tutorial: Graphical Data Analysis
What you get is what you see
Antony
Unwin, Dept of Computer-Oriented Statistics and
Data Analysis University of Augsburg, Germany
Abstract
Graphical data analysis means using graphics to discover and
present information in datasets. This course discusses the
role graphics play in analysis and how they can complement
and support statistical modelling.
Graphical data analysis is useful for data cleaning,
exploring data, identifying trends and clusters, spotting
local patterns, evaluating modeling output, and presenting
results. It is essential for exploratory data analysis and
data mining. R's flexibility and its range of visualization
tools make it an excellent software for graphical analysis.
Outline
-
Introduction
-
Goals, Definitions
-
Data Cleaning
-
Exploratory Data Analysis
-
Interactive methods
-
Conditioning, subsetting, selection sequences
-
EDA in practice (hands-on software session)
-
(coffee break)
-
-
Visualising multivariate data
-
Introduction to Mosaic plots and variations
-
Review of Parallel coordinate plots
-
Dataset discussion session in groups with laptops.
Prerequisites
Participants should have a knowledge of standard statistical
graphics and experience of carrying out data analysis.
Laptops
Participants are welcome to bring their own laptops and
datasets to explore graphical analyses for themselves,
especially in the discussion sessions.
Supporting material
Datasets used in the examples will be available for downloading
in June.
The slides used in the course will be available as a pdf file
for participants at the course.
Please check here for up to date tutorial resources.